Fast Edit Propagation for 360 Degree Panoramas Using Function Interpolation

Abstract

Due to its intuitive stroke-based user interface, edit propagation has wide applications such as image recoloring and relighting, tone editing, image matting, etc. This paper presents a function interpolation method for efficient edit propagation on 360 degree panoramas. Given a panoramic image as input and user-specified strokes as edit hints, our approach adopts an adaptive sampling strategy based on the diversity of local color distribution. By selecting the most representative samples, this strategy can significantly reduce the number of samples. We assume that the projection of the input panorama is known, so that it can be mapped to a 3D unit sphere where the spherical distance metric can be defined. Then edit propagation is formulated as a radial basis function interpolation problem, which can be efficiently solved by using the non-negative linear least squares. We also utilize a multi-resolution strategy and a function look-up table for further acceleration. Experimental results show that our method can efficiently propagate edits on high-resolution panoramas and produce seam-free and smooth editing results.